Litcius/Paper detail

Cosmo

Xiaomin Ouyang, Xian Shuai, Jiayu Zhou, Ivy Wang Shi, Zhiyuan Xie, Guoliang Xing, Jianwei Huang

2022Proceedings of the 28th Annual International Conference on Mobile Computing And Networking84 citationsDOI

Abstract

Human activity recognition (HAR) is a key enabling technology for a wide range of emerging applications. Although multimodal sensing systems are essential for capturing complex and dynamic human activities in real-world settings, they bring several new challenges including limited labeled multimodal data. In this paper, we propose Cosmo, a new system for contrastive fusion learning with small data in multimodal HAR applications. Cosmo features a novel two-stage training strategy that leverages both unlabeled data on the cloud and limited labeled data on the edge. By integrating novel fusion-based contrastive learning and quality-guided attention mechanisms, Cosmo can effectively extract both consistent and complementary information across different modalities for efficient fusion. Our evaluation on a cloud-edge testbed using two public datasets and a new multimodal HAR dataset shows that Cosmo delivers significant improvement over state-of-the-art baselines in both recognition accuracy and convergence delay.

Topics & Concepts

Computer scienceTestbedCloud computingMultimodal learningModalitiesArtificial intelligenceSensor fusionKey (lock)Enhanced Data Rates for GSM EvolutionMachine learningActivity recognitionBig dataData miningWorld Wide WebOperating systemSocial scienceSociologyComputer securityContext-Aware Activity Recognition SystemsIndoor and Outdoor Localization TechnologiesAnomaly Detection Techniques and Applications
Cosmo | Litcius